Hugging Face's logo

mlfoundations-dev
/
stackoverflow_25000tasks_.25p

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
28b7751
·
verified ·
1 Parent(s): 1d73ede

Training in progress, epoch 2

Browse files
Files changed (5) hide show
  1. model-00001-of-00004.safetensors +1 -1
  2. model-00002-of-00004.safetensors +1 -1
  3. model-00003-of-00004.safetensors +1 -1
  4. model-00004-of-00004.safetensors +1 -1
  5. trainer_log.jsonl +5 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d61c21c61aabcc4047d54d8c38af165d469bf9f2ffbb746a4f2e6885b2e1f5d6
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c436287614ea7344f6925269eee6d9eb0de00dfb3c74882b9035990cc286f0b6
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8989192098bd27b6c7ec52942a410012e4879e63a689a1af0e2fb55ce9a35349
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51d5c63ce358b6f047cfac90cbe6a7f27e6d35e3d6e5b94892622c0b70a9f354
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e337c410e24566381764a99978a5f4f7f3fac28a290ab3121403b50e05ffd47
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2d07ddc81c5d74d0d07252d1fec54b4408be78a06eaeb4df6820b19de2c00af
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83945d597075c5ce8af085d9f30bb38141d86d9b3422532bc503ee8ad5979d23
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8aa9bdeade6c4d5de38afc8e4c8a53c35f43a9c599c62dd585f9aefc1bf968c6
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -2,3 +2,8 @@
2
  {"current_steps": 20, "total_steps": 99, "loss": 0.6865, "lr": 5e-06, "epoch": 0.5970149253731343, "percentage": 20.2, "elapsed_time": "0:10:43", "remaining_time": "0:42:21"}
3
  {"current_steps": 30, "total_steps": 99, "loss": 0.648, "lr": 5e-06, "epoch": 0.8955223880597015, "percentage": 30.3, "elapsed_time": "0:16:02", "remaining_time": "0:36:52"}
4
  {"current_steps": 33, "total_steps": 99, "eval_loss": 0.6713858842849731, "epoch": 0.9850746268656716, "percentage": 33.33, "elapsed_time": "0:18:16", "remaining_time": "0:36:32"}
 
 
 
 
 
 
2
  {"current_steps": 20, "total_steps": 99, "loss": 0.6865, "lr": 5e-06, "epoch": 0.5970149253731343, "percentage": 20.2, "elapsed_time": "0:10:43", "remaining_time": "0:42:21"}
3
  {"current_steps": 30, "total_steps": 99, "loss": 0.648, "lr": 5e-06, "epoch": 0.8955223880597015, "percentage": 30.3, "elapsed_time": "0:16:02", "remaining_time": "0:36:52"}
4
  {"current_steps": 33, "total_steps": 99, "eval_loss": 0.6713858842849731, "epoch": 0.9850746268656716, "percentage": 33.33, "elapsed_time": "0:18:16", "remaining_time": "0:36:32"}
5
+ {"current_steps": 40, "total_steps": 99, "loss": 0.6545, "lr": 5e-06, "epoch": 1.1940298507462686, "percentage": 40.4, "elapsed_time": "0:22:53", "remaining_time": "0:33:46"}
6
+ {"current_steps": 50, "total_steps": 99, "loss": 0.5982, "lr": 5e-06, "epoch": 1.4925373134328357, "percentage": 50.51, "elapsed_time": "0:28:11", "remaining_time": "0:27:37"}
7
+ {"current_steps": 60, "total_steps": 99, "loss": 0.5827, "lr": 5e-06, "epoch": 1.7910447761194028, "percentage": 60.61, "elapsed_time": "0:33:29", "remaining_time": "0:21:45"}
8
+ {"current_steps": 67, "total_steps": 99, "eval_loss": 0.6018304228782654, "epoch": 2.0, "percentage": 67.68, "elapsed_time": "0:37:31", "remaining_time": "0:17:55"}
9
+ {"current_steps": 70, "total_steps": 99, "loss": 0.5874, "lr": 5e-06, "epoch": 2.08955223880597, "percentage": 70.71, "elapsed_time": "0:40:22", "remaining_time": "0:16:43"}